© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229395
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     फटा
    0.46
    ecer
    0.38
    固体
    0.37
    ⎟
    0.36
     kazan
    0.36
    䉽
    0.36
    apter
    0.35
     sulfates
    0.34
    uretic
    0.34
    Washington
    0.33
    POSITIVE LOGITS
    بیر
    0.39
    我们会
    0.38
    [{}\
    0.38
    señ
    0.38
    trailing
    0.36
    姒
    0.36
     seam
    0.36
     বীর
    0.36
    WEBPACK
    0.35
     console
    0.35
    Activations Density 0.000%

    No Known Activations